From fce4e1d1b48f23cd8332e60afce3df8d6209a6a7 Mon Sep 17 00:00:00 2001
From: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Date: 星期四, 11 四月 2024 14:59:22 +0800
Subject: [PATCH] SenseVoice对富文本解码的参数 (#1608)
---
funasr/frontends/wav_frontend.py | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/funasr/frontends/wav_frontend.py b/funasr/frontends/wav_frontend.py
index 71cf77a..afa7421 100644
--- a/funasr/frontends/wav_frontend.py
+++ b/funasr/frontends/wav_frontend.py
@@ -32,7 +32,6 @@
rescale_line = line_item[3:(len(line_item) - 1)]
vars_list = list(rescale_line)
continue
- import pdb;pdb.set_trace()
means = np.array(means_list).astype(np.float32)
vars = np.array(vars_list).astype(np.float32)
cmvn = np.array([means, vars])
@@ -76,6 +75,7 @@
LFR_outputs = torch.vstack(LFR_inputs)
return LFR_outputs.type(torch.float32)
+@tables.register("frontend_classes", "wav_frontend")
@tables.register("frontend_classes", "WavFrontend")
class WavFrontend(nn.Module):
"""Conventional frontend structure for ASR.
--
Gitblit v1.9.1